© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20542
    Prev
    Next
    INDEX
    Explanations

    because / due to / reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīįèĥ½å¤Ł
    -0.09
    æīįæľī
    -0.08
    zia
    -0.08
     напÑĢав
    -0.08
    æīįåı¯ä»¥
    -0.08
    ensation
    -0.08
    è´¡çĮ®
    -0.08
     Paolo
    -0.08
    oin
    -0.08
     Bench
    -0.08
    POSITIVE LOGITS
    çļĦåİŁåĽł
    0.19
    ä»Ģä¹ĪåİŁåĽł
    0.18
    æĪĸ许æĺ¯
    0.17
    è¿Ļæĺ¯åĽłä¸º
    0.17
    主è¦ģåİŁåĽł
    0.17
    åİŁåĽłæĺ¯
    0.15
    åİŁåĽł
    0.15
     reasons
    0.15
    æĢİä¹ĪåĽŀäºĭ
    0.15
    æĺ¯åĽłä¸º
    0.15
    Activations Density 0.216%

    No Known Activations